AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Efficient Modality Selection in Multimodal Learning

Yifei He, Runxiang Cheng, Gargi Balasubramaniam, Yao-Hung Hubert Tsai, Han Zhao

JMLR 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use greedy submodular selection (Algorithm 1) instead of random selectionmodality selection · Patch-MNIST (49 and 9 modalities)utility / test accuracyImproved
use greedy selection instead of the average subsetmodality selection · Patch-MNIST (9 modalities)utilityImproved
select with greedy Algorithm 1modality selection · Patch-MNIST (49 modalities)utility: near-maximum utility with 7 modalitiesImproved
add modalities beyond 20 selectedmodality selection · Patch-MNIST (49 modalities)test accuracy: accuracy barely improves after 20 modalitiesNo clear effect
use greedy Algorithm 1 instead of MCI rankingmodality selection · Patch-MNIST (49 modalities)test loss: slightly lower loss below size 15Mixed
use MCI ranking instead of greedy maximizationmodality selection · Patch-MNIST (9 modalities)utilityNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy